Merge pull request #290 from lixianglai/linux-6.6.y

add loongarch kvm support for Linux 6.6.y

Documentation/virt/kvm/api.rst

@@ -416,6 +416,13 @@ Reads the general purpose registers from the vcpu.
 	__u64 pc;
   };
 
+  /* LoongArch */
+  struct kvm_regs {
+	/* out (KVM_GET_REGS) / in (KVM_SET_REGS) */
+	unsigned long gpr[32];
+	unsigned long pc;
+  };
+
 
 4.12 KVM_SET_REGS
 -----------------
@@ -506,7 +513,7 @@ translation mode.
 ------------------
 
 :Capability: basic
-:Architectures: x86, ppc, mips, riscv
+:Architectures: x86, ppc, mips, riscv, loongarch
 :Type: vcpu ioctl
 :Parameters: struct kvm_interrupt (in)
 :Returns: 0 on success, negative on failure.
@@ -592,6 +599,14 @@ b) KVM_INTERRUPT_UNSET
 
 This is an asynchronous vcpu ioctl and can be invoked from any thread.
 
+LOONGARCH:
+^^^^^^^^^^
+
+Queues an external interrupt to be injected into the virtual CPU. A negative
+interrupt number dequeues the interrupt.
+
+This is an asynchronous vcpu ioctl and can be invoked from any thread.
+
 
 4.17 KVM_DEBUG_GUEST
 --------------------
@@ -737,7 +752,7 @@ signal mask.
 ----------------
 
 :Capability: basic
-:Architectures: x86
+:Architectures: x86, loongarch
 :Type: vcpu ioctl
 :Parameters: struct kvm_fpu (out)
 :Returns: 0 on success, -1 on error
@@ -746,7 +761,7 @@ Reads the floating point state from the vcpu.
 
 ::
 
-  /* for KVM_GET_FPU and KVM_SET_FPU */
+  /* x86: for KVM_GET_FPU and KVM_SET_FPU */
   struct kvm_fpu {
 	__u8  fpr[8][16];
 	__u16 fcw;
@@ -761,12 +776,21 @@ Reads the floating point state from the vcpu.
 	__u32 pad2;
   };
 
+  /* LoongArch: for KVM_GET_FPU and KVM_SET_FPU */
+  struct kvm_fpu {
+	__u32 fcsr;
+	__u64 fcc;
+	struct kvm_fpureg {
+		__u64 val64[4];
+	}fpr[32];
+  };
+
 
 4.23 KVM_SET_FPU
 ----------------
 
 :Capability: basic
-:Architectures: x86
+:Architectures: x86, loongarch
 :Type: vcpu ioctl
 :Parameters: struct kvm_fpu (in)
 :Returns: 0 on success, -1 on error
@@ -775,7 +799,7 @@ Writes the floating point state to the vcpu.
 
 ::
 
-  /* for KVM_GET_FPU and KVM_SET_FPU */
+  /* x86: for KVM_GET_FPU and KVM_SET_FPU */
   struct kvm_fpu {
 	__u8  fpr[8][16];
 	__u16 fcw;
@@ -790,6 +814,15 @@ Writes the floating point state to the vcpu.
 	__u32 pad2;
   };
 
+  /* LoongArch: for KVM_GET_FPU and KVM_SET_FPU */
+  struct kvm_fpu {
+	__u32 fcsr;
+	__u64 fcc;
+	struct kvm_fpureg {
+		__u64 val64[4];
+	}fpr[32];
+  };
+
 
 4.24 KVM_CREATE_IRQCHIP
 -----------------------
@@ -1387,7 +1420,7 @@ documentation when it pops into existence).
 -------------------
 
 :Capability: KVM_CAP_ENABLE_CAP
-:Architectures: mips, ppc, s390, x86
+:Architectures: mips, ppc, s390, x86, loongarch
 :Type: vcpu ioctl
 :Parameters: struct kvm_enable_cap (in)
 :Returns: 0 on success; -1 on error
@@ -1442,7 +1475,7 @@ for vm-wide capabilities.
 ---------------------
 
 :Capability: KVM_CAP_MP_STATE
-:Architectures: x86, s390, arm64, riscv
+:Architectures: x86, s390, arm64, riscv, loongarch
 :Type: vcpu ioctl
 :Parameters: struct kvm_mp_state (out)
 :Returns: 0 on success; -1 on error
@@ -1460,7 +1493,7 @@ Possible values are:
 
    ==========================    ===============================================
    KVM_MP_STATE_RUNNABLE         the vcpu is currently running
-                                 [x86,arm64,riscv]
+                                 [x86,arm64,riscv,loongarch]
    KVM_MP_STATE_UNINITIALIZED    the vcpu is an application processor (AP)
                                  which has not yet received an INIT signal [x86]
    KVM_MP_STATE_INIT_RECEIVED    the vcpu has received an INIT signal, and is
@@ -1516,11 +1549,14 @@ For riscv:
 The only states that are valid are KVM_MP_STATE_STOPPED and
 KVM_MP_STATE_RUNNABLE which reflect if the vcpu is paused or not.
 
+On LoongArch, only the KVM_MP_STATE_RUNNABLE state is used to reflect
+whether the vcpu is runnable.
+
 4.39 KVM_SET_MP_STATE
 ---------------------
 
 :Capability: KVM_CAP_MP_STATE
-:Architectures: x86, s390, arm64, riscv
+:Architectures: x86, s390, arm64, riscv, loongarch
 :Type: vcpu ioctl
 :Parameters: struct kvm_mp_state (in)
 :Returns: 0 on success; -1 on error
@@ -1538,6 +1574,9 @@ For arm64/riscv:
 The only states that are valid are KVM_MP_STATE_STOPPED and
 KVM_MP_STATE_RUNNABLE which reflect if the vcpu should be paused or not.
 
+On LoongArch, only the KVM_MP_STATE_RUNNABLE state is used to reflect
+whether the vcpu is runnable.
+
 4.40 KVM_SET_IDENTITY_MAP_ADDR
 ------------------------------
 
@@ -2841,6 +2880,19 @@ Following are the RISC-V D-extension registers:
   0x8020 0000 0600 0020 fcsr      Floating point control and status register
 ======================= ========= =============================================
 
+LoongArch registers are mapped using the lower 32 bits. The upper 16 bits of
+that is the register group type.
+
+LoongArch csr registers are used to control guest cpu or get status of guest
+cpu, and they have the following id bit patterns::
+
+  0x9030 0000 0001 00 <reg:5> <sel:3>   (64-bit)
+
+LoongArch KVM control registers are used to implement some new defined functions
+such as set vcpu counter or reset vcpu, and they have the following id bit patterns::
+
+  0x9030 0000 0002 <reg:16>
+
 
 4.69 KVM_GET_ONE_REG
 --------------------

Documentation/virt/kvm/index.rst

@@ -14,6 +14,7 @@ KVM
    s390/index
    ppc-pv
    x86/index
+   loongarch/index
 
    locking
    vcpu-requests

Documentation/virt/kvm/loongarch/hypercalls.rst

@@ -0,0 +1,79 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+===================================
+The LoongArch paravirtual interface
+===================================
+
+KVM hypercalls use the HVCL instruction with code 0x100, and the hypercall
+number is put in a0 and up to five arguments may be placed in a1-a5, the
+return value is placed in v0 (alias with a0).
+
+The code for that interface can be found in arch/loongarch/kvm/*
+
+Querying for existence
+======================
+
+To find out if we're running on KVM or not, cpucfg can be used with index
+CPUCFG_KVM_BASE (0x40000000), cpucfg range between 0x40000000 - 0x400000FF
+is marked as a specially reserved range. All existing and future processors
+will not implement any features in this range.
+
+When Linux is running on KVM, cpucfg with index CPUCFG_KVM_BASE (0x40000000)
+returns magic string "KVM\0"
+
+Once you determined you're running under a PV capable KVM, you can now use
+hypercalls as described below.
+
+KVM hypercall ABI
+=================
+
+Hypercall ABI on KVM is simple, only one scratch register a0 (v0) and at most
+five generic registers used as input parameter. FP register and vector register
+is not used for input register and should not be modified during hypercall.
+Hypercall function can be inlined since there is only one scratch register.
+
+The parameters are as follows:
+
+        ========	================	================
+	Register	IN			OUT
+        ========	================	================
+	a0		function number		Return code
+	a1		1st parameter		-
+	a2		2nd parameter		-
+	a3		3rd parameter		-
+	a4		4th parameter		-
+	a5		5th parameter		-
+        ========	================	================
+
+Return codes can be as follows:
+
+	====		=========================
+	Code		Meaning
+	====		=========================
+	0		Success
+	-1		Hypercall not implemented
+	-2		Hypercall parameter error
+	====		=========================
+
+KVM Hypercalls Documentation
+============================
+
+The template for each hypercall is:
+1. Hypercall name
+2. Purpose
+
+1. KVM_HCALL_FUNC_PV_IPI
+------------------------
+
+:Purpose: Send IPIs to multiple vCPUs.
+
+- a0: KVM_HCALL_FUNC_PV_IPI
+- a1: lower part of the bitmap of destination physical CPUIDs
+- a2: higher part of the bitmap of destination physical CPUIDs
+- a3: the lowest physical CPUID in bitmap
+
+The hypercall lets a guest send multicast IPIs, with at most 128
+destinations per hypercall.  The destinations are represented by a bitmap
+contained in the first two arguments (a1 and a2). Bit 0 of a1 corresponds
+to the physical CPUID in the third argument (a3), bit 1 corresponds to the
+physical ID a3+1, and so on.

Documentation/virt/kvm/loongarch/index.rst

@@ -0,0 +1,10 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=========================
+KVM for LoongArch systems
+=========================
+
+.. toctree::
+   :maxdepth: 2
+
+   hypercalls.rst

MAINTAINERS

@@ -11527,6 +11527,18 @@ F:	include/kvm/arm_*
 F:	tools/testing/selftests/kvm/*/aarch64/
 F:	tools/testing/selftests/kvm/aarch64/
 
+KERNEL VIRTUAL MACHINE FOR LOONGARCH (KVM/LoongArch)
+M:	Tianrui Zhao <[email protected]>
+M:	Bibo Mao <[email protected]>
+M:	Huacai Chen <[email protected]>
+L:	[email protected]
+L:	[email protected]
+S:	Maintained
+T:	git git://git.kernel.org/pub/scm/virt/kvm/kvm.git
+F:	arch/loongarch/include/asm/kvm*
+F:	arch/loongarch/include/uapi/asm/kvm*
+F:	arch/loongarch/kvm/
+
 KERNEL VIRTUAL MACHINE FOR MIPS (KVM/mips)
 M:	Huacai Chen <[email protected]>
 L:	[email protected]

arch/loongarch/Kbuild

@@ -3,5 +3,7 @@ obj-y += mm/
 obj-y += net/
 obj-y += vdso/
 
+obj-$(CONFIG_KVM) += kvm/
+
 # for cleaning
 subdir- += boot

arch/loongarch/Kconfig

@@ -132,6 +132,7 @@ config LOONGARCH
 	select HAVE_KPROBES
 	select HAVE_KPROBES_ON_FTRACE
 	select HAVE_KRETPROBES
+	select HAVE_KVM
 	select HAVE_MOD_ARCH_SPECIFIC
 	select HAVE_NMI
 	select HAVE_PCI
@@ -266,6 +267,9 @@ config AS_HAS_LASX_EXTENSION
 config AS_HAS_LBT_EXTENSION
 	def_bool $(as-instr,movscr2gr \$a0$(comma)\$scr0)
 
+config AS_HAS_LVZ_EXTENSION
+	def_bool $(as-instr,hvcl 0)
+
 menu "Kernel type and options"
 
 source "kernel/Kconfig.hz"
@@ -562,6 +566,15 @@ config CPU_HAS_PREFETCH
 	bool
 	default y
 
+config PARAVIRT
+	bool "Enable paravirtualization code"
+	depends on AS_HAS_LVZ_EXTENSION
+	help
+          This changes the kernel so it can modify itself when it is run
+	  under a hypervisor, potentially improving performance significantly
+	  over full virtualization.  However, when run without a hypervisor
+	  the kernel is theoretically slower and slightly larger.
+
 config ARCH_SUPPORTS_KEXEC
 	def_bool y
 
@@ -659,3 +672,5 @@ source "kernel/power/Kconfig"
 source "drivers/acpi/Kconfig"
 
 endmenu
+
+source "arch/loongarch/kvm/Kconfig"

arch/loongarch/configs/loongson3_defconfig

@@ -619,6 +619,8 @@ CONFIG_ISCSI_IBFT=m
 CONFIG_EFI_ZBOOT=y
 CONFIG_EFI_CAPSULE_LOADER=m
 CONFIG_EFI_TEST=m
+CONFIG_VIRTUALIZATION=y
+CONFIG_KVM=m
 CONFIG_MTD=m
 CONFIG_MTD_BLOCK=m
 CONFIG_MTD_CFI=m

arch/loongarch/include/asm/Kbuild

@@ -24,4 +24,3 @@ generic-y += poll.h
 generic-y += param.h
 generic-y += posix_types.h
 generic-y += resource.h
-generic-y += kvm_para.h

arch/loongarch/include/asm/hardirq.h

@@ -12,11 +12,16 @@
 extern void ack_bad_irq(unsigned int irq);
 #define ack_bad_irq ack_bad_irq
 
+enum ipi_msg_type {
+	IPI_RESCHEDULE,
+	IPI_CALL_FUNCTION,
+};
 #define NR_IPI	2
 
 typedef struct {
 	unsigned int ipi_irqs[NR_IPI];
 	unsigned int __softirq_pending;
+	atomic_t message ____cacheline_aligned_in_smp;
 } ____cacheline_aligned irq_cpustat_t;
 
 DECLARE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);